Interactive Health Apps May Inspire Healthy Behaviors, but Watch the Tone

Just like real doctors and nurses, online health tools with good - but controlled - communication skills can promote healthier lifestyles, according to researchers. However, if their tone is conversational, these tools may lull users into a false sense of comfort, they add. In a study, people who experienced a back-and-forth interaction with an online health risk assessment website were more likely to follow the health behaviors suggested by the tool, according to S. Shyam Sundar, Distinguished Professor of Communications and co-director of the Media Effects Research Laboratory.

"This shows that delivering information on health risks through dialogue can help users get engaged with the tool and may positively affect their health," said Sundar. "In general, it speaks to the design of interactive delivery of health information that it is not only engaging, but also inspiring."

The researchers, who present their findings in the current issue of Human Communication Research, suggest that the display of interconnected questions and answers promotes a feeling of contingency and that leads to better engagement with the site. Better engagement, then, may increase the likelihood that the user will adopt strategies for better health.

"When you are having this back and forth interaction with a system -- you are having a conversation with that system," said Sundar. "We think that interactivity has been achieved when the system's output is contingent on the user's input in a continuous threaded way."

Although the back-and-forth feel of a conversation could lead to improved health intentions, a more conversational tone in the messages may make users feel less susceptible to health risks such as obesity, diabetes and heart disease, according to Sundar, who worked with Saraswathi Bellur, assistant professor of communication, University of Connecticut.

The study found that when the online tool used short phrases, such as "Mm-hmm" and "Go on" to promote an informal conversational tone, users felt less susceptible to health risks, according to Bellur.

"This conversational tone may make them warm and fuzzy, but that's not what you want to do with a health assessment tool," Bellur said. "If you want people to stand up and take action, this type of friendly turn-taking softens the effect. However, if the goal of the interaction is to promote a sense of comfort among individuals, the same conversational tone strategy could work well, with the online tool acting like a virtual coach and providing reassurance," she added.

The researchers suggest that as more people become frustrated with the lack of face-to-face interaction with their doctors, patients may be more willing to try online health assessments and applications. In 2012, 61 percent of people said they were dissatisfied with the time doctors spent talking with patients, according to a poll conducted by National Public Radio, the Robert Wood Johnson Foundation and the Harvard School of Public Health.

"We are seeing a growth in e-medicine," Sundar said. "People are trying to compensate for this lack of face-to-face time with doctors by using online tools, which are becoming increasingly conversational."

The design of these e-health tools need not be highly sophisticated, according to the researchers.

"A simple instant-message-like feature that enables a dialogue between the user and the system is sufficient to evoke rich perceptions of interactivity, which, in turn, could favorably influence health behaviors and attitudes," said Bellur. "Therein lies the power of interactive health tools."

The researchers recruited 172 undergraduate students to take part in the study. Participants were assigned to one of six versions of a health risk assessment website. The sites were designed to have either low, medium, or high interactivity with either conversational or no conversational tone.

Participants took part in a question and answer session delivered through the website's instant messaging interface. The low-interactivity site did not display any signs or visual cues that there was an ongoing interaction between the user and the system. The medium-interactivity site visually called out the user's response in a box titled "Your response." In the high-interactivity condition, the system referred to the user's previous answers by displaying "previously, you mentioned" or "earlier, you reported" following his or her answers.

Websites with more conversational tone added phrases such as "Let's move onto the next question" and "OK, let's talk about exercise" during the question and answer session.

The U.S. National Science Foundation supported this work.

Bellur, S. and Sundar, S. S.
Talking Health With a Machine: How Does Message Interactivity Affect Attitudes and Cognitions?
Hum Commun Res, 43: 25–53, doi: 10.1111/hcre.12094.

Most Popular Now

AI-Powered CRISPR could Lead to Faster G…

Stanford Medicine researchers have developed an artificial intelligence (AI) tool to help scientists better plan gene-editing experiments. The technology, CRISPR-GPT, acts as a gene-editing “copilot” supported by AI to help...

Groundbreaking AI Aims to Speed Lifesavi…

To solve a problem, we have to see it clearly. Whether it’s an infection by a novel virus or memory-stealing plaques forming in the brains of Alzheimer’s patients, visualizing disease processes...

AI Spots Hidden Signs of Depression in S…

Depression is one of the most common mental health challenges, but its early signs are often overlooked. It is often linked to reduced facial expressivity. However, whether mild depression or...

AI Tools Help Predict Severe Asthma Risk…

Mayo Clinic researchers have developed artificial intelligence (AI) tools that help identify which children with asthma face the highest risk of serious asthma exacerbation and acute respiratory infections. The study...

ChatGPT 4o Therapeutic Chatbot 'Ama…

One of the first randomized controlled trials assessing the effectiveness of a large language model (LLM) chatbot 'Amanda' for relationship support shows that a single session of chatbot therapy...

AI Model Forecasts Disease Risk Decades …

Imagine a future where your medical history could help predict what health conditions you might face in the next two decades. Researchers have developed a generative AI model that uses...

AI Distinguishes Glioblastoma from Look-…

A Harvard Medical School–led research team has developed an AI tool that can reliably tell apart two look-alike cancers found in the brain but with different origins, behaviors, and treatments. The...

AI Model Indicates Four out of Ten Breas…

A project at Lund University in Sweden has trained an AI model to identify breast cancer patients who could be spared from axillary surgery. The model analyses previously unutilised information...

Smart Device Uses AI and Bioelectronics …

As a wound heals, it goes through several stages: clotting to stop bleeding, immune system response, scabbing, and scarring. A wearable device called "a-Heal," designed by engineers at the University...

Overcoming the AI Applicability Crisis a…

Opinion Article by Harry Lykostratis, Chief Executive, Open Medical. The government’s 10 Year Health Plan makes a lot of the potential of AI-software to support clinical decision making, improve productivity, and...

Dartford and Gravesham Implements Clinis…

Dartford and Gravesham NHS Trust has taken a significant step towards a more digital future by rolling out electronic test ordering using Clinisys ICE. The trust deployed the order communications...